[ad_1]
DDPM, Steady Diffusion, DALL·E-2, Imagen, Kandinsky 2, SDEdit, ControlNet, InstructPix2Pix, and extra
Embracing the ever-growing curiosity in Generative AI, together with picture era, many wonderful assets are beginning to change into accessible, a few of which I’ll spotlight beneath. Nevertheless, based mostly on my expertise, progressing past foundational programs calls for vital effort, as assets on superior subjects change into extra scattered.
On this article, we’ll record the preferred diffusion fashions from the Hugging Face Diffusers library, which is the first instrument for using this know-how. We’ll present temporary explanations of those fashions, evaluate them, and description their strengths and weaknesses.
The construction of this text is as follows: we’ll begin by reviewing just a few beneficial assets for individuals who are simply starting to review diffusion fashions. Afterward, we’ll present a quick clarification of the HuggingFace pipelines. Lastly, we’ll delve deep into every pipeline listed within the Popular Tasks & Pipelines part of the Diffusers GitHub repository.
[ad_2]
Source link
